Hugging Face's logo

matt-guay
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
matt-guay commited on
Commit
12a4f9d
·
1 Parent(s): 1cef89d

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  3. config.yml +3 -3
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  8. results.json +1 -1
  9. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 883.00 +/- 353.92
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,13 +62,13 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 32),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
- ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
- ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 705.00 +/- 142.74
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 64),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
+ ('exploration_final_eps', 0.001),
70
  ('exploration_fraction', 0.1),
71
+ ('frame_stack', 10),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 967129541
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 769665766
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,16 +1,16 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
- - 0.01
10
  - - exploration_fraction
11
  - 0.1
12
  - - frame_stack
13
- - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
+ - 0.001
10
  - - exploration_fraction
11
  - 0.1
12
  - - frame_stack
13
+ - 10
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ced6777b5a2703087ce173f2b1023c20cab743bcc15bf6499c31828abc2b5ab8
3
- size 27225073
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f0a1b156d017a9fcbd6ccd660e9fb39af3a3983b8a6156b67c364ad150d6b92
3
+ size 27705812
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0160c4adc04f74e11512b453e640733df5c44834936cdb90cea978af7b15bb4
3
- size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:884b117b71acf94b958ab6452a1cd87b7e84ebe5bf6c724842f30245e8bd6ddb
3
+ size 13604043
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:902189f4401fb7f7faec826c3d0b25b73713a999e07fa1b9184416afb0caf7ac
3
- size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b4736a0b0567f5a3851db03ff0039199cfc97eafbcca4b92376f40e48c48b1
3
+ size 13603241
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 883.0, "std_reward": 353.9152440910111, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-22T00:35:06.685636"}
 
1
+ {"mean_reward": 705.0, "std_reward": 142.74102423620198, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-22T22:57:14.604623"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecc0e1016d0877516e6397b23c87649da05a872fdc46ffae7247c44946050f25
3
- size 271752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2522ff203f49567f24ae934e7d59c7a35c575f1a4c27316ff3b9f49452a456c
3
+ size 289371